New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Model Training (dropout, batchsize, STFT?) #9
Comments
leolya
changed the title
Model Training (dropout and batchsize?)
Model Training (dropout, batchsize, STFT?)
May 3, 2022
Hi @leolya ,
|
Thanks for your reply! It is really helpful! @Sanyuan-Chen Another small question: Is a "step" in the paper means an update with a full batch? If I'm using gradient accumulation, I need to train for more steps? |
Yes, one step means one parameter update, i.e. |
Thanks for replying! |
Did you train the model successfully? I try to train the model but find that the loss does not go down |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Thanks for sharing the code. I have some questions about model training.
"The 25 ms frame size with the frame shift of 10 ms is usedfor feature generation. A 512-point FFT size and hamming win-dow are used in (i)STFT, forming the 257-dimentional masksand spectrum. The log spectrogram with utterance-wise meanvariance normalization is extracted as the input feature for allthe separation models."
The text was updated successfully, but these errors were encountered: